The Descent of Hierarchy, and Selection in Relational Semantics

In many types of technical texts, meaning is embedded in noun compounds. A language understanding program needs to be able to interpret these in order to ascertain sentence meaning. We explore the possibility of using the top levels of an existing lexical hierarchy for the purpose of placing words from a noun compound into categories, and then using this category membership to determine the relation that holds between the words. Since lexical hierarchies are not necessarily ideally suited for this task, we pose the question: how far down the hierarchy must the algorithm descend before all the terms within the subhierarchy behave uniformly with respect to the semantic relation in question? We present the results of an analysis on two-word noun compounds from the biomedical domain which suggests that we can obtain classification accuracy of approximately 90% while generalizing well over the data.